Facial Recognition Based Smart Door Lock System

Abstract

In recent times, there has been a growing interest in smart home systems particularly with the advent of Internet of Things (IOT). One of the important aspects of the smart home system is the security and access control. In this paper, a facial recognition security system was designed using Raspberry Pi which can be seamlessly integrated to the smart home system. Eigenface was used for the feature extraction, while Principal Component Analysis (PCA) was used as the classifier. The output of facial recognition algorithm was connected to the relay circuit which controls a magnetic lock placed at the door. Overall results obtained were very promising with 90% accuracy in facial recognition. Facial recognition accuracy can be improved by employing a hierarchical image processing approach to reduce the training or testing time.